What Is The Turing Test?

Today’s computers have become the true testament of what a multipurpose machine can be. However, even though we’ve come quite far in the computing world, one of the milestones that Computer Science and Artificial Intelligence researchers would still like to achieve is a machine that can reach human-level intelligence. Although this is far easier said than done, there was a test developed back in the 1950s to determine this exact qualification. It was a test to design machine intelligence. The Turing Test, to this day, stands as the gold standard for scientists to test their machines and they keep the Turing Test rules as the paradigm from which they judge. Now, before we get into the what the Turing Test is, let’s first take a look at the history of this legendary test.

Mechanical Pinochio

(Photo Credit : Pasimi/Wikimedia Commons)

History

Frans_Hals_-_Portret_van_René_Descartes

(Photo Credit : Wikimedia Commons)

The question of whether it was possible to make a thinking machine first developed on a philosophical forefront, rather than a scientific one. Rene Descartes is the first person who took up this question in a less scientifically rigorous way. He delved into the possibility of automata that could respond to the interactions of humans. Here, the term automata can be understood as a self-operating machine. Descartes goes on to also claim that such machines will never be able to communicate back with any significant amount of intelligence. Yet this is where the Descartes failed to foresee, unlike Turing, that future machines would be able to overcome such an inefficiency.

Alan_Turing_Aged

(Photo Credit : Wikimedia Commons)

The term ‘machine intelligence’ was loosely being thrown around ten years before the inception of the field of Artificial Intelligence. It was a common topic among the members of the Ratio Club. The Ratio Club consisted of members and researchers in the field of cybernetics and electronics of the time. Alan Turing, who was part of this group, came up with this test and in his honor, the test was named after him. Alan Turing had been tackling the notion of machine intelligence as early as 1941. He coined the term “computer intelligence” in the year 1947. It was in one of his most historic reports that Turing brought about the question of whether or not it was possible for machinery to show intelligent behavior. There are several forms of the Turing Test that are employed to check the intelligence of a machine.

Imitation Game and Standard Interpretation

Concerning the Turing Test, it is widely accepted that there are three standards to it. The first two are in accordance with the standard of “Computing Machinery and Intelligence”, which Alan Turing himself set up. The third one, which is a relatively hot button topic and widely debated, is known as “Standard Interpretation.” There are some qualms regarding the Standard Interpretation as a legitimate variation of the test, or whether it is nothing more than a misreading of his paper. Each of these variations has its own strengths and weakness.

https://en.wikipedia.org/wiki/Turing_test#/media/File:Turing_test_diagram.png

(Photo Credit : Juan Alberto Sánchez Margallo/Wikimedia Commons)

The original publication that Turing wrote, which laid the framework for the Turing Test, was a simple party game involving three players. Let’s name these players A, B, and C. In this game, let’s assume that player A is male, player B is female and player C, who plays the role of the interrogator, can be either of the two sexes. Now, let’s place both the players behind a screen, compartmentalized and anonymously. By asking questions to player A and player B, player C tries to gauge who is the male and who is the female. By asking a series of questions, player C tries to evaluate which one is male and female. In this, player A’s role is to trick the interrogator (player C), while player B must make an effort to assist the interrogator in making the right decision. Turing then goes on to ask, what would happen when a machine takes the place of player A in this game. Will the machine be able to fool the interrogator? Will the machine be able to think on its own? A second version appeared by Turing in a 1950 paper.  However, in this imitation game, the role of player A is performed by the computer, and the role of player B is played by either a man or woman.

Now, the point of the Turing Test must be clearly understood. It’s not to fool the interrogator, but to act as a measure of how closely a computer can behave like a human. In the standard interpretation, player A is a computer and player B is a person of either sex. The role of the interrogator is not to determine which is male and which is female, but rather which is a computer and which is a human. The fundamental issue with the standard interpretation is that the interrogator cannot differentiate which responder is human and which is the machine. There are issues about duration, but the standard interpretation generally considers this limitation as something that should be reasonable. In conclusion, we can state that even though the Turing Test does have its fallacies, it remains one of the most prominent tests we can use to test the intelligence of computers!

References:

  1. Turing Test
  2. Alan Turing
The short URL of the present article is: http://sciabc.us/5qVvi
Help us make this article better
About the Author:

Venkatesh is an Electrical and Electronics Engineer from SRM Institute of Science and Technology, India. He is deeply fascinated by Robotics and Artificial Intelligence. He is also a chess aficionado, He likes studying chess classics from the 1800 and 1900’s. He enjoys writing about science and technology as he finds the intricacies which come with each topic fascinating.

.
Science ABC YouTube Videos

  1. What Happens If You Skydive Off The International Space Station?
  2. Does Earth Come Back To The Same Spot In Space Every Year On Your Birthday?
  3. What Happens When A Bird Strikes An Aircraft?
  4. How Does Google Maps Works: How Is It So Incredibly Accurate About Traffic Conditions?
  5. 10 Things About The Solar System Your Teachers Never Told You
  6. What Happens When Something Travels Faster Than The Speed of Light?
  7. Entropy: Why is it Predicted to Cause the Heat Death of the Universe?
  8. Science of a Rocket Launch: How do Rockets Work?

Related Articles



Get more stuff like this
in your inbox

Subscribe to our mailing list and get interesting stuff and updates to your email inbox.